RSI Arena: Towards Recursive Self-Improvement with Human Feedback
Paper • 2610.33624 • Published • 24
AI & ML interests
We develop data-driven computational methods and intelligent systems to facilitate decision making.
Recent Activity
View all activity
Papers
Uncovering Cross-Objective Interference in Multi-Objective Alignment
A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain
franciscoliuÂ
authored 20
papers 1 day ago
Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research
Paper • 2610.24944 • Published • 24
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning
Paper • 2402.04401 • Published
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
Paper • 2510.14738 • Published
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
Paper • 2609.39820 • Published • 31
CheatBench: Measuring Reward Gaming in AI Agents
Paper • 2609.36308 • Published • 5
Superficial Self-Improved Reasoners Benefit from Model Merging
Paper • 2503.02103 • Published
Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
Paper • 2502.15910 • Published
Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
Paper • 2502.06872 • Published • 8
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Paper • 2410.22108 • Published • 1
Machine Unlearning in Generative AI: A Survey
Paper • 2407.20516 • Published
Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
Paper • 2608.26372 • Published • 2
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
Paper • 2608.21544 • Published • 1
Avoiding Copyright Infringement via Large Language Model Unlearning
Paper • 2406.10952 • Published
MemoHarness: Agent Harnesses That Learn from Experience
Paper • 2607.14159 • Published • 2
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
Paper • 2606.05080 • Published • 32
Instant Personalized Large Language Model Adaptation via Hypernetwork
Paper • 2510.16282 • Published
Behavior Knowledge Merge in Reinforced Agentic Models
Paper • 2601.13572 • Published • 27
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
Paper • 2605.10664 • Published • 8
OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG
Paper • 2601.09028 • Published • 34